© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107499
    Prev
    Next
    INDEX
    Explanations

    past events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intens
    -0.32
    该
    -0.27
    æŨ
    -0.27
    ited
    -0.26
    对æīĭ
    -0.25
    纽
    -0.25
    à¸Ńà¸ģ
    -0.24
    çĸĨ
    -0.24
     EXPER
    -0.24
    éĩįéĩı
    -0.24
    POSITIVE LOGITS
    aat
    0.25
    OrDefault
    0.25
    othermal
    0.25
    orm
    0.24
    _PROVID
    0.23
    *Math
    0.23
    conversation
    0.23
    ansa
    0.23
     Matthews
    0.22
    Parm
    0.22
    Activations Density 8.344%

    No Known Activations